Are visual dictionaries generalizable?

05/11/2012
by   Otávio A. B. Penatti, et al.
0

Mid-level features based on visual dictionaries are today a cornerstone of systems for classification and retrieval of images. Those state-of-the-art representations depend crucially on the choice of a codebook (visual dictionary), which is usually derived from the dataset. In general-purpose, dynamic image collections (e.g., the Web), one cannot have the entire collection in order to extract a representative dictionary. However, based on the hypothesis that the dictionary reflects only the diversity of low-level appearances and does not capture semantics, we argue that a dictionary based on a small subset of the data, or even on an entirely different dataset, is able to produce a good representation, provided that the chosen images span a diverse enough portion of the low-level feature space. Our experiments confirm that hypothesis, opening the opportunity to greatly alleviate the burden in generating the codebook, and confirming the feasibility of employing visual dictionaries in large-scale dynamic environments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2019

A Fast Dictionary Learning Method for Coupled Feature Space Learning

In this letter, we propose a novel computationally efficient coupled dic...
research
03/21/2013

Separable Dictionary Learning

Many techniques in computer vision, machine learning, and statistics rel...
research
06/16/2015

Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning

In histopathological image analysis, feature extraction for classificati...
research
02/28/2018

Learning Discriminative Multilevel Structured Dictionaries for Supervised Image Classification

Sparse representations using overcomplete dictionaries have proved to be...
research
01/29/2017

Extracting Bilingual Persian Italian Lexicon from Comparable Corpora Using Different Types of Seed Dictionaries

Bilingual dictionaries are very important in various fields of natural l...
research
01/31/2020

Learning Deep Analysis Dictionaries – Part I: Unstructured Dictionaries

Inspired by the recent success of Deep Neural Networks and the recent ef...
research
01/05/2015

Group K-Means

We study how to learn multiple dictionaries from a dataset, and approxim...

Please sign up or login with your details

Forgot password? Click here to reset